© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89412
    Prev
    Next
    INDEX
    Explanations

    metallic, digital, therefore, ponytail, thousands

    np_acts-logits-general · gemini-2.5-flash-lite

    vaccination Jenner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    9
    0.55
     као
    0.50
    s
    0.47
     perte
    0.47
    बहन
    0.47
    6
    0.45
     fiable
    0.45
    ｸ
    0.45
     גם
    0.44
    ttä
    0.44
    POSITIVE LOGITS
     まし
    0.45
     ChangeNotifier
    0.45
     내용을
    0.45
     পক্ষে
    0.44
     중심으로
    0.44
     断
    0.44
     推
    0.43
    anan
    0.43
     쪽
    0.43
    ishops
    0.43
    Activations Density 0.001%

    No Known Activations